© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 40134
    Prev
    Next
    INDEX
    Explanations

    references to notable artists, artworks, and their cultural contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    á»IJ
    -0.07
    afx
    -0.07
    ãĤĪãģĨãģ§ãģĻ
    -0.07
    æŁĦ
    -0.07
    endregion
    -0.06
    alternative
    -0.06
    ạnh
    -0.06
    .Payload
    -0.06
    Alternative
    -0.06
    /callback
    -0.06
    POSITIVE LOGITS
    's
    0.11
    ’s
    0.10
    çļĦ
    0.09
     çļĦ
    0.08
    ìĿĺ
    0.07
    çĶ¨çļĦ
    0.07
    çļĦå°ı
    0.07
    기ìĿĺ
    0.07
    ãĤ¹ãģ®
    0.07
    çĶŁçļĦ
    0.07
    Activations Density 0.027%

    No Known Activations